CN103489212A - Two-dimensional shape corresponding method based on user inspiration - Google Patents
Two-dimensional shape corresponding method based on user inspiration Download PDFInfo
- Publication number
- CN103489212A CN103489212A CN201310420958.1A CN201310420958A CN103489212A CN 103489212 A CN103489212 A CN 103489212A CN 201310420958 A CN201310420958 A CN 201310420958A CN 103489212 A CN103489212 A CN 103489212A
- Authority
- CN
- China
- Prior art keywords
- dimensional shapes
- summit
- dimensional
- shapes
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses a two-dimensional shape corresponding method based on user inspiration. From the aspect of two sets of given two-dimensional shapes, one or more pairs of corresponding relations between the two sets of two-dimensional shapes are specified by a user first, and the corresponding relations between other unspecified two-dimensional shapes between the two sets of two-dimensional shapes are further established by using an algorithm. According to the two-dimensional shape corresponding method based on the user inspiration, the corresponding relations between the two sets of shapes are allowed to be controlled by the user, and only a small amount of user interaction is needed so that the shape corresponding result capable of 'meeting user needs' can be generated. The two-dimensional shape corresponding method based on the user inspiration has the advantages of being small in user interaction amount, high in corresponding efficiency, simple, accurate and efficient in algorithm, capable of correcting errors easily, and simple in coding.
Description
Technical field
The present invention relates to the corresponding technical field of two-dimensional shapes, relate in particular to a kind of two-dimensional shapes corresponding method inspired based on the user.
Background technology
Under the active support of the government, domestic animation industry development in recent years is rapid, and animation output also significantly promotes.Yet traditional Freehandhand-drawing 2 D animation needs a large amount of Production Times and great number cost of manufacture.For the aided two-dimensional cartoon making, many two-dimension cartoon making business softwares have been researched and developed both at home and abroad, such as Adobe Flash, Toon Boom Studio etc.These business softwares have mainly realized so-called " paperless cartoon " function, drawing on traditional animation teacher paper are transferred to and allow the animation teacher paint on computers by Digitizing plate, with editor and the management that facilitates cartoon material.But the animation teacher still needs to draw one by one the 2 D animation sequence, workload is still very huge.
Therefore, research and develop intelligentized 2 D animation technology, automatically to generate the 2 D animation sequence, thereby effectively improve the make efficiency of 2 D animation and reduce its cost of manufacture, there is real society and economic implications.
The two-dimensional shapes interpolation is an important technology in the computer animation field, is widely used in two-dimentional key frame vector animation system.This technology can realize in adjacent key frame comprise role's attitude smooth transition, thereby automatically generate the role animation sequence between key frame.In actual two-dimensional vector animation, role's attitude is meaned to form by one group of (a plurality of) two-dimensional shapes usually, and each shape correspondence role's a feature.For the smooth transition between two groups of shapes that realize meaning adjacent two role's attitudes, the two-dimensional shapes interpositioning need to solve a basic problem: the feature on associated two role's attitudes how, how to set up two groups of one-to-one relationships between shape.When drawing role's attitude, the animation teacher can be by draw the upper corresponding shape of each feature of role according to a definite sequence, automatically to realize the shape correspondence between adjacent role's attitude.But this will greatly limit animation teacher's freedom of creation, final impact creation efficiency and quality.A kind of simple effective method is to allow the user specify to set up two groups of correspondences between shape by craft, but this needs more man-machine interactively, thereby has reduced make efficiency.Although people have proposed some automatic shape corresponding method, these methods can not guarantee to produce the corresponding result of shape of " meeting user's needs ", still need more manual interaction to correct result.Therefore, how to reduce the man-machine interactively amount and guarantee that producing correct corresponding result is the problem that the two-dimensional shapes corresponding method is needed solution badly.
China Patent Publication No. CN101903908A, open day is on Dec 01st, 2010, discloses a kind of 2D/3D image registration based on feature.It comprises following methods: property detector, and it is configured for from two dimensional image and extracts the two dimensional character collection, from 3-D view, extracts the three-dimensional feature collection; The projection process device, it is configured for three-dimensional data is projected into to two-dimensional projection data; And registration processor, it is configured for regulates parameter so that described two dimensional character collection and the described three-dimensional feature collection by the projection of described projection process device use perspective geometry are carried out to registration, and the parameter of use through regulating is to be used the described 3-D view of described perspective geometry projection to carry out registration by described two dimensional image with by described projection process device.Weak point is, this 2D/3D method for registering images based on feature, when the feature set correspondence makes a mistake, the projection process device can not be corrected its corresponding mistake, can not adopt algorithm to carry out the Automatic-searching coupling to its corresponding mistake, thereby it is not high to mate corresponding accuracy.
Summary of the invention
The present invention is the deficiency that interactive quantity is large, error correction is difficult, the Corresponding matching accuracy is not high existed in existing complete manual or fully automatic two-dimensional shapes corresponding method in order to solve, provide a kind of precisely efficient, error correction is easy, coding is simple, efficiently a kind of two-dimensional shapes corresponding method inspired based on the user of algorithm.
To achieve these goals, the present invention is by the following technical solutions:
A kind of two-dimensional shapes corresponding method inspired based on the user, comprise the steps:
(1-1) role's attitude of setting in the two-dimensional vector animation is comprised of one group of two-dimensional shapes, and each two-dimensional shapes is corresponding with a role characteristic; The user specifies two role's attitudes
with
at least one pair of corresponding relation between interior two-dimensional shapes;
Set G
1in arbitrary summit
corresponding
in the two-dimensional shapes of
set G
2in arbitrary summit
corresponding
in a two-dimensional shapes
set
the fillet threshold value be L
1, set
the fillet threshold value be L
2;
G
1by following step, set up: work as G
1in the distance of two corresponding two-dimensional shapes in any summit be less than L
1the time, between described two any summits, set up a fillet;
G
2by following step, set up: work as G
2in the distance of two corresponding two-dimensional shapes in any summit be less than L
2the time, between described two any summits, set up a fillet;
(1-3) utilize following algorithm to set up
with
one-to-one relationship between interior two-dimensional shapes:
Wherein,
be respectively two-dimensional shapes
size, towards and outward appearance;
be respectively two-dimensional shapes
size, towards and outward appearance;
(1-3-2) specified every pair of two-dimensional shapes of corresponding relation for the user, at connection layout G
1and G
2middlely finding out respectively this to the corresponding summit of shape, is a pair of associated summit pair by this to apex marker;
(1-3-3) set G
1and G
2in arbitraryly to incident vertex, to comprised summit, be:
with
wherein,
be positioned at G
1in,
be positioned at G
2in; Will
with
adjacent vertex in not yet associated summit put into respectively set P and Q;
(1-3-4) will gather any summit in P
with any summit in Q
be associated, form a pair of candidate association summit pair, utilize the similarity measurement scaling function to calculate
with
the degree of association
wherein,
for
corresponding shape,
for
corresponding shape;
(1-3-5) when the candidate association summit is greater than zero to number, choose all degrees of association
in maximal value
will
corresponding candidate association summit is to being labeled as associated summit pair, and this summit to corresponding two shape correspondences together; Return to step (1-3-3);
When equalling zero to number in the candidate association summit, G
1and G
2correspondence between the corresponding two groups of shapes in middle summit completes.
The two-dimensional shapes interpolation is an important technology in the computer animation field, is widely used in two-dimentional key frame vector animation system.This technology can realize in adjacent key frame comprise role's attitude smooth transition, thereby automatically generate the role animation sequence between key frame.
For solve in adjacent key frame comprise role's attitude the smooth transition problem, need to be at first by two role's attitudes of the same role of adjacent key frame
with
one-to-one relationship between interior two-dimensional shapes.
The problem to be solved in the present invention is exactly how efficiently and exactly to set up two groups of corresponding relations between shape.
The two-dimensional shapes corresponding method inspired based on the user of the present invention is from two groups of given two-dimensional shapes, at first the user specifies one or more pairs of corresponding relations between two groups of two-dimensional shapes, and uses algorithm is further set up the corresponding relation between other unspecified two-dimensional shapes between two groups of two-dimensional shapes.Method of the present invention allows the user to control two groups of corresponding relations between shape, and only needs a small amount of user interactions can produce the corresponding result of shape of " meeting user's needs ".The present invention has solved the correspondence problem between two groups of two-dimensional shapes effectively, can be efficiently and set up exactly corresponding relation between any two groups of shapes.
As preferably, in step (1-2), also comprise the steps:
The curve of described any two corresponding two-dimensional shapes in summit is carried out respectively discrete, calculate the mean place of all discrete points of every curve, mean place is made as to the center of gravity of corresponding two-dimensional shapes;
Calculate the distance between the center of gravity of described any two corresponding two-dimensional shapes in summit, the distance between the center of gravity of two-dimensional shapes is made as to the distance between two-dimensional shapes;
Select
in arbitrary two-dimensional shapes, calculate described two-dimensional shapes and arrive
in the distance of other two-dimensional shapes, the mean value of getting each distance is fillet threshold value L
1;
Select
in arbitrary two-dimensional shapes, calculate described two-dimensional shapes and arrive
in the distance of other two-dimensional shapes, the mean value of getting each distance is fillet threshold value L
2.
As preferably, described
for two-dimensional shapes
total arc length; Described
for initial point arrives two-dimensional shapes
the vector that forms of center of gravity and the angle of forward x axle;
for two-dimensional shapes
on the number of vision significance point.
As preferably, described
for two-dimensional shapes
total arc length;
for initial point arrives shape
the vector that forms of center of gravity and the angle of forward x axle;
for shape
the number of upper vision significance point.
As preferably, described conspicuousness point comprises point with extreme curvature and end points.
The present invention can reach following effect: (1) amount of user interaction is little, and corresponding efficiency is high; (2) algorithm is simple, accurate, efficient, and error correction is easy, and coding is simple.
The accompanying drawing explanation
Fig. 1 is a kind of process flow diagram of embodiments of the invention;
Fig. 3 of the present inventionly specifies two two-dimensional character attitudes after a pair of shape corresponding relation by the user
with
Fig. 4 is two the corresponding two-dimensional attitude figure that complete of the present invention.
Embodiment
Embodiment as shown in Figure 1 is a kind of two-dimensional shapes corresponding method inspired based on the user, comprises the steps:
Step 100, role's attitude of setting in the two-dimensional vector animation is comprised of one group of two-dimensional shapes, and as shown in Figure 2, each two-dimensional shapes is corresponding with a role characteristic; As shown in Figure 3, the user specifies two role's attitudes
with
a pair of corresponding relation 3 between interior two-dimensional shapes;
Set G
1in arbitrary summit
corresponding
in the two-dimensional shapes of
; Set G
2in arbitrary summit
corresponding
in a two-dimensional shapes
; Set
the fillet threshold value be L
1, set
the fillet threshold value be L
2;
G
1by following step, set up: work as G
1in the distance of two corresponding two-dimensional shapes in any summit be less than L
1the time, between described two any summits, set up a fillet;
G
2by following step, set up: work as G
2in the distance of two corresponding two-dimensional shapes in any summit be less than L
2the time, between described two any summits, set up a fillet;
In the present embodiment, the curve of described any two corresponding two-dimensional shapes in summit is carried out respectively discrete, calculate the mean place of all discrete points of every curve, mean place is made as to the center of gravity of corresponding two-dimensional shapes;
Calculate the distance between the center of gravity of described any two corresponding two-dimensional shapes in summit, the distance between the center of gravity of two-dimensional shapes is made as to the distance between two-dimensional shapes;
Select
in arbitrary two-dimensional shapes, calculate described two-dimensional shapes and arrive
in the distance of other two-dimensional shapes, the mean value of getting each distance is fillet threshold value L
1;
Select
in arbitrary two-dimensional shapes, calculate described two-dimensional shapes and arrive
in the distance of other two-dimensional shapes, the mean value of getting each distance is fillet threshold value L
2.
Step 300, utilize following algorithm to set up
with
one-to-one relationship between interior two-dimensional shapes:
Wherein,
be respectively two-dimensional shapes
size, towards and outward appearance;
be respectively two-dimensional shapes
size, towards and outward appearance;
for two-dimensional shapes
total arc length; Described
for initial point arrives two-dimensional shapes
the vector that forms of center of gravity and the angle of forward x axle;
for two-dimensional shapes
on the number of vision significance point.
for two-dimensional shapes
total arc length;
for initial point arrives shape
the vector that forms of center of gravity and the angle of forward x axle;
for shape
the number of upper vision significance point.The conspicuousness point comprises point with extreme curvature and end points.
Step 302, specified every pair of two-dimensional shapes of corresponding relation, at connection layout G for the user
1and G
2middlely finding out respectively this to the corresponding summit of shape, is a pair of associated summit pair by this to apex marker;
Step 303, set G
1and G
2in arbitraryly to incident vertex, to comprised summit, be:
with
wherein,
be positioned at G
1in,
be positioned at G
2in; Will
with
adjacent vertex in not yet associated summit put into respectively set P and Q;
Step 304, by any summit in set P
with any summit in Q
be associated, form a pair of candidate association summit pair, utilize the similarity measurement scaling function to calculate
with
the degree of association
wherein,
for
corresponding shape,
for
corresponding shape;
Step 305, when the candidate association summit is greater than zero to number, choose all degrees of association
in maximal value
will
corresponding candidate association summit is to being labeled as associated summit pair, and this summit to corresponding two shape correspondences together; Return to step 303;
As shown in Figure 4, when equalling zero to number in the candidate association summit, G
1and G
2correspondence between the corresponding two groups of shapes in middle summit completes.
Should be understood that the present embodiment only is not used in and limits the scope of the invention for the present invention is described.Should be understood that in addition those skilled in the art can make various changes or modifications the present invention after the content of having read the present invention's instruction, these equivalent form of values fall within the application's appended claims limited range equally.
Claims (5)
1. the two-dimensional shapes corresponding method inspired based on the user, is characterized in that, comprises the steps:
(1-1) role's attitude of setting in the two-dimensional vector animation is comprised of one group of two-dimensional shapes, and each two-dimensional shapes is corresponding with a role characteristic; The user specifies two role's attitudes
with
at least one pair of corresponding relation between interior two-dimensional shapes;
Set G
1in arbitrary summit
corresponding
in the two-dimensional shapes of
set G
2in arbitrary summit
corresponding
in a two-dimensional shapes
set
the fillet threshold value be L
1, set
the fillet threshold value be L
2;
G
1by following step, set up: work as G
1in the distance of two corresponding two-dimensional shapes in any summit be less than L
1the time, between described two any summits, set up a fillet;
G
2by following step, set up: work as G
2in the distance of two corresponding two-dimensional shapes in any summit be less than L
2the time, between described two any summits, set up a fillet;
(1-3) utilize following algorithm to set up
with
one-to-one relationship between interior two-dimensional shapes:
Wherein,
be respectively two-dimensional shapes
size, towards and outward appearance;
be respectively two-dimensional shapes
size, towards and outward appearance;
(1-3-2) specified every pair of two-dimensional shapes of corresponding relation for the user, at connection layout G
1and G
2middlely finding out respectively this to the corresponding summit of shape, is a pair of associated summit pair by this to apex marker;
(1-3-3) set G
1and G
2in arbitraryly to incident vertex, to comprised summit, be:
with
wherein,
be positioned at G
1in,
be positioned at G
2in; Will
with
adjacent vertex in not yet associated summit put into respectively set P and Q;
(1-3-4) will gather any summit in P
with any summit in Q
be associated, form a pair of candidate association summit pair, utilize the similarity measurement scaling function to calculate
with
the degree of association
wherein,
for
corresponding shape,
for
corresponding shape;
(1-3-5) when the candidate association summit is greater than zero to number, choose all degrees of association
in maximal value
will
corresponding candidate association summit is to being labeled as associated summit pair, and this summit to corresponding two shape correspondences together; Return to step (1-3-3);
When equalling zero to number in the candidate association summit, G
1and G
2correspondence between the corresponding two groups of shapes in middle summit completes.
2. the two-dimensional shapes corresponding method inspired based on the user according to claim 1, is characterized in that, in step (1-2), also comprises the steps:
The curve of described any two corresponding two-dimensional shapes in summit is carried out respectively discrete, calculate the mean place of all discrete points of every curve, mean place is made as to the center of gravity of corresponding two-dimensional shapes;
Calculate the distance between the center of gravity of described any two corresponding two-dimensional shapes in summit, the distance between the center of gravity of two-dimensional shapes is made as to the distance between two-dimensional shapes;
Select
in arbitrary two-dimensional shapes, calculate described two-dimensional shapes and arrive
in the distance of other two-dimensional shapes, the mean value of getting each distance is fillet threshold value L
1;
3. the two-dimensional shapes corresponding method inspired based on the user according to claim 1, is characterized in that, described
for two-dimensional shapes
total arc length; Described
for initial point arrives two-dimensional shapes
the vector that forms of center of gravity and the angle of forward x axle;
for two-dimensional shapes
on the number of vision significance point.
4. the two-dimensional shapes corresponding method inspired based on the user according to claim 1, is characterized in that, described
for two-dimensional shapes
total arc length;
for initial point arrives shape
the vector that forms of center of gravity and the angle of forward x axle;
for shape
the number of upper vision significance point.
5. according to the described two-dimensional shapes corresponding method inspired based on the user of claim 3 or 4, it is characterized in that, described conspicuousness point comprises point with extreme curvature and end points.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310420958.1A CN103489212B (en) | 2013-09-16 | 2013-09-16 | The two-dimensional shapes corresponding method inspired based on user |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310420958.1A CN103489212B (en) | 2013-09-16 | 2013-09-16 | The two-dimensional shapes corresponding method inspired based on user |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103489212A true CN103489212A (en) | 2014-01-01 |
CN103489212B CN103489212B (en) | 2016-09-28 |
Family
ID=49829409
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310420958.1A Active CN103489212B (en) | 2013-09-16 | 2013-09-16 | The two-dimensional shapes corresponding method inspired based on user |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103489212B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104424658A (en) * | 2014-10-22 | 2015-03-18 | 浙江工商大学 | Structure-preserving interpolation method of two-dimensional shapes |
CN107633543A (en) * | 2017-08-21 | 2018-01-26 | 浙江工商大学 | Consider the stripe shape corresponding method of local topology |
CN107978010A (en) * | 2017-11-27 | 2018-05-01 | 浙江工商大学 | Accurate shape matching process stage by stage |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070118024A1 (en) * | 2005-11-23 | 2007-05-24 | General Electric | Iterative vascular identification |
US20090251465A1 (en) * | 2008-04-03 | 2009-10-08 | Peter Hassenpflug | Method for Interpolating an intermediate polygon p from two polygons p1 and p2 |
CN101996245A (en) * | 2010-11-09 | 2011-03-30 | 南京大学 | Form feature describing and indexing method of image object |
CN102622773A (en) * | 2012-02-14 | 2012-08-01 | 浙江工商大学 | Interactive two-dimensional shape feature corresponding method |
-
2013
- 2013-09-16 CN CN201310420958.1A patent/CN103489212B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070118024A1 (en) * | 2005-11-23 | 2007-05-24 | General Electric | Iterative vascular identification |
US20090251465A1 (en) * | 2008-04-03 | 2009-10-08 | Peter Hassenpflug | Method for Interpolating an intermediate polygon p from two polygons p1 and p2 |
CN101996245A (en) * | 2010-11-09 | 2011-03-30 | 南京大学 | Form feature describing and indexing method of image object |
CN102622773A (en) * | 2012-02-14 | 2012-08-01 | 浙江工商大学 | Interactive two-dimensional shape feature corresponding method |
Non-Patent Citations (2)
Title |
---|
杨文武,冯结青,王勋: "基于多层次特征结构的二维形状渐变", 《计算机辅助设计与图形学学报》 * |
杨文武,冯结青,金小刚,彭群生: "基于特征分解的2-D多边形渐变", 《软件学报》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104424658A (en) * | 2014-10-22 | 2015-03-18 | 浙江工商大学 | Structure-preserving interpolation method of two-dimensional shapes |
CN104424658B (en) * | 2014-10-22 | 2017-09-29 | 浙江工商大学 | A kind of two-dimensional shapes interpolating method of structure-preserving |
CN107633543A (en) * | 2017-08-21 | 2018-01-26 | 浙江工商大学 | Consider the stripe shape corresponding method of local topology |
CN107633543B (en) * | 2017-08-21 | 2020-12-08 | 浙江工商大学 | Line shape corresponding method considering local topological structure |
CN107978010A (en) * | 2017-11-27 | 2018-05-01 | 浙江工商大学 | Accurate shape matching process stage by stage |
CN107978010B (en) * | 2017-11-27 | 2021-03-05 | 浙江工商大学 | Staged precise shape matching method |
Also Published As
Publication number | Publication date |
---|---|
CN103489212B (en) | 2016-09-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103606186B (en) | The virtual hair style modeling method of a kind of image and video | |
CN103617603B (en) | A kind of self-repairing method of 3-dimensional digital geometric mesh model structure | |
CN104809755B (en) | Three-dimensional rebuilding method based on single image cultural relic ruins | |
CN101383055B (en) | Three-dimensional human face constructing method and system | |
CN102306386B (en) | Method for quickly constructing third dimension tree model from single tree image | |
CN103310443B (en) | High-resolution remote sensing image immediate processing method and system | |
CN104933755A (en) | Static object reconstruction method and system | |
CN104361632A (en) | Triangular mesh hole-filling method based on Hermite radial basis function | |
CN102831638A (en) | Three-dimensional human body multi-gesture modeling method by adopting free-hand sketches | |
CN104123747A (en) | Method and system for multimode touch three-dimensional modeling | |
CN105913444B (en) | Livestock figure profile reconstructing method and Body Condition Score method based on soft laser ranging | |
CN105975655B (en) | A kind of imitative Tang and Song Dynasty ancient architecture abnormity roofing tile parametric modeling method based on BIM | |
CN106547724A (en) | Theorem in Euclid space coordinate transformation parameter acquisition methods based on minimum point set | |
CN107273543A (en) | A kind of conversion method of DGN data formats | |
CN112712596A (en) | Dense matching point cloud building structured model fine reconstruction method | |
CN103489212A (en) | Two-dimensional shape corresponding method based on user inspiration | |
CN103955960B (en) | Image viewpoint transformation method based on single input image | |
CN107327143A (en) | A kind of special-shaped structures the construction line-putting method of landscape engineering | |
CN105741340B (en) | A kind of transmission line of electricity three-dimensional scenic emulation mode and system for web page display | |
CN104424658A (en) | Structure-preserving interpolation method of two-dimensional shapes | |
CN103473766B (en) | A kind of two-dimensional shape feature Point matching method of view-based access control model perception | |
CN104318552A (en) | Convex hull projection graph matching based model registration method | |
CN105243137A (en) | Draft-based three-dimensional model retrieval viewpoint selection method | |
CN109767492A (en) | A kind of distance computation method of substation's threedimensional model | |
CN105574886A (en) | High-precision calibration method of handheld multi-lens camera |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20201223 Address after: No.477 Yongle Road, Wangdian Town, Xiuzhou District, Jiaxing City, Zhejiang Province Patentee after: ZHEJIANG OUTUO ELECTRICAL Co.,Ltd. Address before: 310018, No. 18 Jiao Tong Street, Xiasha Higher Education Park, Hangzhou, Zhejiang Patentee before: ZHEJIANG GONGSHANG University |